Comment on AI chatbots unable to accurately summarise news, BBC finds

tal@lemmy.today ⁨2⁩ ⁨months⁩ ago

• JackGreenEarth@lemm.ee ⁨2⁩ ⁨months⁩ ago

  Surely you’d need TTS for that one, too? Which one do you use, is it open weights?

  source

  • brucethemoose@lemmy.world ⁨2⁩ ⁨months⁩ ago

    Zephyra just came out, seems sick:

    huggingface.co/Zyphra

    There are also some “native” tts LLMs like GLM 9B, which “capture” more information in the output than pure text input.

    source

    • ag10n@lemmy.world ⁨2⁩ ⁨months⁩ ago

      A website with zero information, and barely anything on their huggingface page. What’s exciting about this?

      source

      • brucethemoose@lemmy.world ⁨2⁩ ⁨months⁩ ago

        Whoops, yeah, should have linked the blog.

        I didn’t want to link the individual models because I’m not sure hybrid or pure transformers is better?

        source

        • -> View More Comments
• JohnEdwa@sopuli.xyz ⁨2⁩ ⁨months⁩ ago

  Yeah, out of all the generative AI fields, voice generation at this point is like 95% there in its capability of producing convincing speech even with consumer level tech like ElevenLabs. That last 5% might not even be solvable currently, as it’s those moments it gets the feeling, intonation or pronunciation wrong when the only context you give it is a text input.

  Especially voice cloning - the DRG Cortana Mission Control mod is one of the examples I like to use.

  source